Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    instances of the word "see" and its various forms in conjunction with expressions of perception or observation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soever
    -0.18
    rien
    -0.18
    stery
    -0.16
    unken
    -0.16
    .synthetic
    -0.15
    sole
    -0.15
    vrier
    -0.15
    yl
    -0.14
    umd
    -0.14
    serie
    -0.14
    POSITIVE LOGITS
    /he
    0.35
     fit
    0.29
     how
    0.28
    -through
    0.24
    /read
    0.24
    dust
    0.23
     evidence
    0.22
     through
    0.22
    -eye
    0.20
     proof
    0.19
    Act Density 0.169%

    No Known Activations